© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3144
    Prev
    Next
    INDEX
    Explanations

    violent and sensitive events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     according
    0.42
    iladi
    0.42
     impressively
    0.40
     obvi
    0.38
    !
    0.38
     набира
    0.37
     नवे
    0.37
    晟
    0.36
     into
    0.36
     arrived
    0.36
    POSITIVE LOGITS
     assassination
    0.51
     murderous
    0.48
     falsch
    0.46
    ч
    0.46
     সক্র
    0.45
    睾
    0.44
     قتل
    0.44
    謗
    0.43
     crucifixion
    0.43
    सी
    0.42
    Activations Density 0.111%

    No Known Activations